Welcome!

I am a Member of Technical Staff at Cohere, working on RL post-training.

Previously, I was a research engineer at Reality Defender. Prior to that, I conducted machine learning research in the Machine Learning for Language (ML²) group at New York University. At ML², I had the privilege of being advised by Dr. Cheolhyoung Lee and Prof. Kyunghyun Cho, and having closely worked with Dr. Jason Phang and Prof. Sam Bowman.

Academic Background


M.S. Courant Institute, New York University
  • Computer Science
  • CeDiD: 23FD-I09H-E3IW
B.A. Courant Institute, New York University
  • Computer Science and a minor in Mathematics
  • CeDiD: 22LH-QC4F-EFIF

Research


Command A: An Enterprise-Ready Large Language Model

Team Cohere (including Eugene Choi)
Technical report
tl;dr: a technical report detailing the development of Cohere's latest flagship model, Command A.

Self-Improving Robust Preference Optimization

Eugene Choi, Arash Ahmadian, Matthieu Geist, Oilvier Pietquin, Mohammad Gheshlaghi Azar
ICLR 2025
tl;dr: SRPO is a robust direct alignment method that unlocks inference time self-refinement capability.

Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion

Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub, Eugene Choi, Bill Wu, Chris Cremer, Arash Ahmadian, Yash Chandak, Mohammad Gheshlaghi Azar, Olivier Pietquin, Matthieu Geist
EMNLP 2024
tl;dr: CoPG is a scalable, principled RL algorithm that estimates the optimal policy from off‐policy data.

A Non-monotonic Self-terminating Language Model

Eugene Choi, Kyunghyun Cho, Cheolhyoung Lee
ICLR 2023
tl;dr: our proposed method prevents non-terminating sequences resulting from incomplete decoding algorithms.

Teaching


External

African Masters of Machine Intelligence (AMMI)
  • Deep Learning for NLP: a modern NLP foundations class by Profs Kyunghyun Cho, Duygu Ataman
  • May 2022, Teaching Assistant / Lab Instructor (virtual)

At New York University

DS-UA 203: Machine Learning for Language Understanding
  • A research-oriented class on natural language understanding (NLU) by Prof. Sam Bowman
  • Spring 2022, Section Leader / Teaching Assistant (in-person)

Projects


A Survey of Transfer Learning in Uncertainty Aware Computer-Aided Diagnosis

Eugene Choi, Jeff Cui
CSCI-GA 2271-001: Computer Vision (by Prof. Rob Fergus), Dec. 2021
[paper] [code]

  • Brain tumor segmentation demo:
  • brain tumor seg demo
  • Kidney tumor segmentation demo:
  • kidney tumor seg demo


Website layout credits to Richard Pang. Thanks! :)